DEPLOY

Open-weight LLM comparison

Command R+ vs DeepSeek V3

Side-by-side

Straight from each model's release page and Hugging Face card. Memory shown is for the weights alone: add roughly 15% for real serving. Bold column marks the more parameters and the smaller memory footprint.

FieldCommand R+DeepSeek V3
Total parameters104 B671 B
Active parameters (MoE)—37 B
ArchitecturedenseMoE (671B total, 37B active per token)
VendorCohereDeepSeek
LicenseCC-BY-NC-4.0 (non-commercial)MIT
Released2024-04-042024-12-26
Weights @ FP16208 GB1342 GB
Weights @ INT8104 GB671 GB
Weights @ INT452 GB336 GB

Which is smarter (published benchmarks)

Vendor-reported quality scores on the standard leaderboards. Bold column marks the higher score on the same test.

BenchmarkCommand R+DeepSeek V3
MMLU (5-shot)75.788.5
HumanEval70.782.6
MATH (0-shot)not published61.6
GPQAnot published59.1

Sources: Command R+ model card · DeepSeek V3 model card. Benchmark methodology and prompt template can shift these numbers by several points, so treat these as relative rankings, not absolute scores.

Common questions

Command R+ vs DeepSeek V3: which is bigger?

DeepSeek V3 has more parameters (Command R+: 104 B; DeepSeek V3: 671 B). More parameters usually means higher ceiling on capability and higher memory requirement, though MoE architectures decouple total parameters from per-token compute.

Command R+ vs DeepSeek V3: which is newer?

DeepSeek V3 released 2024-12-26; Command R+ released 2024-04-04.

Command R+ vs DeepSeek V3: which needs less memory to serve?

Command R+ needs less HBM. Weights-only footprint at FP16: Command R+ 208 GB; DeepSeek V3 1342 GB. Half those numbers at INT8, quarter at INT4. Real serving adds 10-30% for KV cache.

Command R+ vs DeepSeek V3: which license is more permissive?

Command R+: CC-BY-NC-4.0 (non-commercial). DeepSeek V3: MIT. Apache 2.0 and MIT allow unrestricted commercial use; Llama Community License allows commercial use but restricts training larger models on outputs; CC-BY-NC and vendor-specific licenses (Qwen 72B, Gemma) have narrower terms. Check the model card for the exact clauses.

See also: every LLM comparison · Command R+ full page · DeepSeek V3 full page.